Accurate and Scalable Matching of Translators to Displaced Persons for Overcoming Language Barriers

TL;DR

This paper presents a scalable machine learning system that efficiently matches translators to displaced persons during crises, significantly reducing response times and improving aid delivery in multilingual emergency situations.

Contribution

It introduces a simple logistic regression model that accurately predicts translator responses, enabling scalable and fast matching in humanitarian contexts.

Findings

Matches 82% of requests with high accuracy

Median response time of 59 seconds

Effective in diverse language crisis scenarios

Abstract

Residents of developing countries are disproportionately susceptible to displacement as a result of humanitarian crises. During such crises, language barriers impede aid workers in providing services to those displaced. To build resilience, such services must be flexible and robust to a host of possible languages. \textit{Tarjimly} aims to overcome the barriers by providing a platform capable of matching bilingual volunteers to displaced persons or aid workers in need of translating. However, Tarjimly's large pool of translators comes with the challenge of selecting the right translator per request. In this paper, we describe a machine learning system that matches translator requests to volunteers at scale. We demonstrate that a simple logistic regression, operating on easily computable features, can accurately predict and rank translator response. In deployment, this lightweight system matches 82\% of requests with a median response time of 59 seconds, allowing aid workers to accelerate their services supporting displaced persons.